← Back to community benchmarks
gemma-4-31b-it
Performance
64k
tokens
197.8
PP tok/s
12.5
TG tok/s
331242
TTFT (ms)
45.1
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 248.9 | 18.7 | 31.8 GB | view |
| 4k | 253.3 | 18.2 | 34.5 GB | view |
| 8k | 251.4 | 17.7 | 35.0 GB | view |
| 64k | 197.8 | 12.5 | 45.1 GB | current |
| 128k | 153.7 | 8.6 | 57.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.7 | 1.00× |
| 2× | 31.3 | 1.67× |
| 4× | 38.8 | 2.07× |